Computers & Industrial Engineering最新文献

{"title":"Assessing product and warranty sales: Impact of assessments and supply chains","authors":"Keang Zhang ,&nbsp;Tao Zhang ,&nbsp;Shang Gao","doi":"10.1016/j.cie.2024.110758","DOIUrl":"10.1016/j.cie.2024.110758","url":null,"abstract":"<div><div>Extended warranties are widely utilized in our lives to help mitigate potential losses. They can be offered either by the manufacturer (in supply chain M) or by a platform (in supply chain R). The decision of a customer to purchase an extended warranty primarily depends on the perceived quality. Customers derive their perceived quality through online assessments of the product found on video-sharing platforms. However, both unbiased and biased online assessments can lead to varying perceptions among customers. In this paper, we propose four models based on two assessments (biased and unbiased) and two supply chain structures (supply chain M and supply chain R). Furthermore, to explore the endogenous nature of biased assessments, we investigate the sponsorship dynamics concerning online assessment bloggers. Key findings include: (1) Underestimation (overestimation) can lead to reduced (increased) profits for both the manufacturer and the platform in supply chain M. However, in supply chain R, underestimation (overestimation) may prove advantageous (detrimental) for the platform. (2) Under unbiased assessments, the optimal retail price of a product in supply chain R consistently surpasses that in supply chain M. With biased assessments, when the actual quality is relatively high, the manufacturer earns more in supply chain M, while the platform earns more in supply chain R. (3) Sponsorship costs escalate with higher actual quality, prompting the manufacturer to allocate a higher sponsorship budget compared to the platform. (4) The extended warranty provider is advised against sponsoring online assessment bloggers. Conversely, the party not providing the extended warranty is recommended for sponsorship of bloggers.</div></div>","PeriodicalId":55220,"journal":{"name":"Computers & Industrial Engineering","volume":"200 ","pages":"Article 110758"},"PeriodicalIF":6.7,"publicationDate":"2025-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143180719","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Optimizing mixed-model assembly line efficiency under uncertain demand: A Q-Learning-Inspired differential evolution algorithm","authors":"Kai Meng,&nbsp;Shujuan Li,&nbsp;Zhoupeng Han","doi":"10.1016/j.cie.2024.110743","DOIUrl":"10.1016/j.cie.2024.110743","url":null,"abstract":"<div><div>Modern manufacturing heavily relies on mixed-model assembly lines to streamline production processes for various product configurations. However, most existing research in this area primarily focuses on deterministic demand scenarios, leaving the challenges posed by uncertain demand relatively unexplored. Such uncertainty can significantly impact assembly line efficiency, resource utilization, and throughput rates. This paper explores the complexities of balancing and sequencing in mixed-model assembly lines, particularly under conditions of uncertain demand. The proposed approach includes a robust mixed-integer linear programming model formulated to optimize production efficiency across diverse scenarios characterized by uncertain demand. To address this complex problem, a novel Q-Learning-Inspired Differential Evolution Algorithm (QL-DE) has been developed. This algorithm utilizes a population-based evolutionary operator, an intra-population crossover operator, six task-centric and three product-centric neighborhood exploration operators, along with a Q-learning-inspired strategy. These components collectively enable the QL-DE algorithm to adaptively handle uncertain demand while optimizing assembly line processes. Finally, through a comparative analysis with five variants and five evolutionary algorithms, the QL-DE approach demonstrates its superior capability in efficiently addressing uncertain demand scenarios and optimizing the performance of mixed-model assembly lines.</div></div>","PeriodicalId":55220,"journal":{"name":"Computers & Industrial Engineering","volume":"200 ","pages":"Article 110743"},"PeriodicalIF":6.7,"publicationDate":"2025-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143181800","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Net benefit-oriented condition-based maintenance for lithium-ion battery packs in SGLS systems: Combining degradation updating and decision-making","authors":"Mengzi Zhen ,&nbsp;Zhen Chen ,&nbsp;Biao Lu ,&nbsp;Zhaoxiang Chen ,&nbsp;Ershun Pan","doi":"10.1016/j.cie.2024.110850","DOIUrl":"10.1016/j.cie.2024.110850","url":null,"abstract":"<div><div>Driven by global sustainability goals, the integration of renewable energy into power grids has significantly increased the demand for advanced battery management solutions. In source-grid-load-storage (SGLS) systems, effective operation and maintenance (O&amp;M) of lithium-ion battery packs (LiBPs) are critical for balancing energy supply, ensuring operational reliability, and enhancing economic viability. However, existing maintenance strategies often fail to address the combined impacts of benefits, risks, and costs and instead rely on inflexible criteria, such as fixed failure thresholds, which are insufficient for managing batteries. Additionally, these strategies lack adaptability and do not incorporate real-time data, limiting their effectiveness in managing the stochastic dependence and inherent randomness of battery degradation. To address these limitations, this paper presents a dynamic condition-based maintenance (DCBM) strategy. This approach employs degradation modeling and parameters updating via a multivariate Wiener process, utilizing real-time data to refine decision-making. It introduces a novel net benefit-oriented model that integrates energy storage benefits, risk losses, and maintenance costs. By framing the problem as a Markov decision process (MDP), an improved algorithm is developed to optimize decisions throughout the battery’s lifecycle. Numerical analyses demonstrate that the proposed approach manages battery degradation uncertainties more effectively than traditional methods. This research provides an economically viable strategy for maintaining battery energy storage systems (BESSs), incorporating financial, safety, and maintenance considerations, thereby contributing to broader sustainability and efficiency goals.</div></div>","PeriodicalId":55220,"journal":{"name":"Computers & Industrial Engineering","volume":"200 ","pages":"Article 110850"},"PeriodicalIF":6.7,"publicationDate":"2025-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143181824","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Research on incentive strategies and cost-sharing mechanisms for cross-regional pollution control","authors":"Min Song ,&nbsp;Yongzeng Lai ,&nbsp;Lin Li","doi":"10.1016/j.cie.2024.110791","DOIUrl":"10.1016/j.cie.2024.110791","url":null,"abstract":"<div><div>Regional environmental collaborative governance is an effective way of addressing increasingly complex and severe environmental pollution. This study constructs a differential game model for regional collaborative governance consisting of the central government and two heterogeneous local governments. From a dynamic game perspective, we compare and analyze the game equilibrium solutions of each participant under five scenarios: noncooperation, vertical compensation, horizontal compensation, comprehensive compensation, and collaborative governance. In addition, this study constructs a dynamically consistent cost-sharing scheme that considers each participant’s fairness concerns. The results indicate that compared to non-cooperative situations, vertical, horizontal, and comprehensive ecological compensation mechanisms achieve a reduction in pollution emission levels and costs as well as an increase in emission reduction efforts in underdeveloped areas. Second, the effect of comprehensive ecological compensation is better than that of horizontal compensation, which is superior to the effect of vertical compensation. Third, compared to ecological compensation mechanisms, the collaborative governance model is more effective in pollution control, not only in improving central government intervention and the pollution reduction level of local governments, but also in reducing governance costs. Finally, the bargaining power and degree of fairness concern for each player can affect the cost-sharing ratio. Additionally, underdeveloped regions tend to form alliances with developed regions and negotiate with the central government to reduce pollution control costs. The research conclusions can provide a theoretical reference for improving ecological compensation mechanisms and strengthening the long-term mechanisms of regional collaborative governance.</div></div>","PeriodicalId":55220,"journal":{"name":"Computers & Industrial Engineering","volume":"200 ","pages":"Article 110791"},"PeriodicalIF":6.7,"publicationDate":"2025-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143181753","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"MERCI: Multi-agent reinforcement learning for enhancing on-demand Electric taxi operation in terms of Rebalancing, Charging, and Informing Orders","authors":"Jiawei Wang ,&nbsp;Haiming Cai ,&nbsp;Lijun Sun ,&nbsp;Binliang Li ,&nbsp;Jian Wang","doi":"10.1016/j.cie.2024.110711","DOIUrl":"10.1016/j.cie.2024.110711","url":null,"abstract":"<div><div>The development of intelligent transportation systems is being driven by the increasing electrification and the Internet of Things. On-demand electric taxis (OETs) are seen as a potential way to meet personalized travel needs and improve transport efficiency. While research is being done to create a multi-agent reinforcement learning (MARL)-based framework to achieve intelligent operation, there are still challenges to be addressed, such as the balance between exploration and exploitation, and the non-stationary issue. This study proposes an ensemble MARL framework to manage the daily operations of OETs, such as rebalancing, charging and informing orders. To address the non-stationary issue caused by the dynamic nature of operations, a demand awareness augmented architecture is proposed to use order information to make better decisions. Experiments using real-world data in Shenzhen show the emergence of intelligence of the proposed framework during operation and its superiority over traditional greedy methods. Additionally, ablation studies demonstrate that the proposed framework outperforms basic MARL architectures.</div></div>","PeriodicalId":55220,"journal":{"name":"Computers & Industrial Engineering","volume":"200 ","pages":"Article 110711"},"PeriodicalIF":6.7,"publicationDate":"2025-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143179719","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Improving the X̄-control chart: A novel scheme based on runs and scans rules","authors":"Tribhuvan Singh ,&nbsp;Nirpeksh Kumar","doi":"10.1016/j.cie.2024.110852","DOIUrl":"10.1016/j.cie.2024.110852","url":null,"abstract":"<div><div>To enhance the performance of Shewhart-type control charts for detecting small to moderate shifts, various schemes based on runs and scans rules have been introduced in the literature. This paper introduces a novel scheme based on runs and scans statistics, known as the improved modified runs and scans rules scheme. The proposed runs and scans rules scheme has been applied to the <span><math><mover><mrow><mi>X</mi></mrow><mrow><mo>̄</mo></mrow></mover></math></span>-chart and its performance has been evaluated in terms of average run length <span><math><mrow><mo>(</mo><mi>ARL</mi><mo>)</mo></mrow></math></span>, standard deviation of run length <span><math><mrow><mo>(</mo><mi>SDRL</mi><mo>)</mo></mrow></math></span> and extra quadratic loss <span><math><mrow><mo>(</mo><mi>EQL</mi><mo>)</mo></mrow></math></span>. The results indicate that newly scheme outperforms the existing competitive runs and scans rules schemes. The effectiveness of the improved modified runs and scans rules scheme is demonstrated through a case study of a white millbase process.</div></div>","PeriodicalId":55220,"journal":{"name":"Computers & Industrial Engineering","volume":"200 ","pages":"Article 110852"},"PeriodicalIF":6.7,"publicationDate":"2025-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143180692","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"SPINEX-TimeSeries: Similarity-based predictions with explainable neighbors exploration for time series and forecasting problems","authors":"Ahmad Z. Naser ,&nbsp;M.Z. Naser","doi":"10.1016/j.cie.2024.110812","DOIUrl":"10.1016/j.cie.2024.110812","url":null,"abstract":"<div><div>This paper introduces a new addition to the SPINEX (Similarity-based Predictions with Explainable Neighbors Exploration) family, tailored specifically for time series and forecasting analysis. This new algorithm leverages the concept of similarity and higher-order temporal interactions across multiple time scales to enhance predictive accuracy and interpretability in forecasting. To evaluate the effectiveness of SPINEX, we present comprehensive benchmarking experiments comparing it against 18 algorithms and across 49 synthetic and real datasets characterized by varying trends, seasonality, and noise levels. Our performance assessment focused on forecasting accuracy and computational efficiency. Our findings reveal that SPINEX consistently ranks among the top 5 performers in forecasting precision and has a superior ability to handle complex temporal dynamics compared to commonly adopted algorithms. Moreover, the algorithm’s explainability features, Pareto efficiency, and medium complexity (on the order of O(log n)) are demonstrated through detailed visualizations to enhance the prediction and decision-making process. We note that integrating similarity-based concepts opens new avenues for research in predictive analytics, promising more accurate and transparent decision making.</div></div>","PeriodicalId":55220,"journal":{"name":"Computers & Industrial Engineering","volume":"200 ","pages":"Article 110812"},"PeriodicalIF":6.7,"publicationDate":"2025-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143181752","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Deep reinforcement learning for machine scheduling: Methodology, the state-of-the-art, and future directions","authors":"Maziyar Khadivi ,&nbsp;Todd Charter ,&nbsp;Marjan Yaghoubi ,&nbsp;Masoud Jalayer ,&nbsp;Maryam Ahang ,&nbsp;Ardeshir Shojaeinasab ,&nbsp;Homayoun Najjaran","doi":"10.1016/j.cie.2025.110856","DOIUrl":"10.1016/j.cie.2025.110856","url":null,"abstract":"<div><div>Machine scheduling aims to optimally assign jobs to a single or a group of machines while meeting manufacturing rules as well as job specifications. Optimizing the machine schedules leads to significant reduction in operational costs, adherence to customer demand, and rise in production efficiency. Despite its benefits for the industry, machine scheduling remains a challenging combinatorial optimization problem to be solved, inherently due to its Non-deterministic Polynomial-time (NP) hard nature. Deep Reinforcement Learning (DRL) has been regarded as a foundation for <em>“artificial general intelligence”</em> with promising results in tasks such as gaming and robotics. Researchers have also aimed to leverage the application of DRL, attributed to extraction of knowledge from data, across variety of machine scheduling problems since 1995. This paper presents a comprehensive review and comparison of the methodology, application, and the advantages and limitations of different DRL-based approaches. Further, the study categorizes the DRL methods based on the integrated computational components including conventional neural networks, encoder–decoder architectures, graph neural networks and metaheuristic algorithms. Our literature review concludes that the DRL-based approaches surpass the performance of exact solvers, heuristics, and tabular reinforcement learning algorithms in either computation speed, generating near-global optimal solutions, or both. They have been applied to static or dynamic scheduling of different machine environments, which consist of single machine, parallel machine, flow shop, job shop, and open shop, with different job characteristics. Nonetheless, the existing DRL-based schedulers face limitations not only in considering complex operational constraints, and configurable multi-objective optimization but also in dealing with generalization, scalability, intepretability, and robustness. Therefore, addressing these challenges shapes future work in this field. This paper serves the researchers to establish a proper investigation of state of the art and research gaps in DRL-based machine scheduling and can help the experts and practitioners choose the proper approach to implement DRL for production scheduling.</div></div>","PeriodicalId":55220,"journal":{"name":"Computers & Industrial Engineering","volume":"200 ","pages":"Article 110856"},"PeriodicalIF":6.7,"publicationDate":"2025-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143180693","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"An innovative framework for optimizing discrete berth allocation and quay crane assignment problems","authors":"Xi Xiang,&nbsp;Xuqiang Chang,&nbsp;Lin Gong,&nbsp;Xin Liu","doi":"10.1016/j.cie.2024.110827","DOIUrl":"10.1016/j.cie.2024.110827","url":null,"abstract":"<div><div>This paper delves into the complexities linked with discrete berth allocation and quay crane assignment within automated container terminals, analyzing scenarios that involve both time-invariant and time-variant considerations. We propose a novel approach, redefining discrete berth allocation and time-invariant quay crane assignment problems as resource-constrained project scheduling problems, which are addressed with an efficient branch and cut algorithm. Furthermore, our investigation extends to the domain of time-variant specific quay crane assignment, introducing a purpose-designed two-stage algorithm for effective resolution. Numerical experiments affirm the efficacy of these algorithms in effectively addressing the intricate yet pivotal challenges inherent in automated terminal operations.</div></div>","PeriodicalId":55220,"journal":{"name":"Computers & Industrial Engineering","volume":"200 ","pages":"Article 110827"},"PeriodicalIF":6.7,"publicationDate":"2025-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143181747","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"HGNP: A PCA-based heterogeneous graph neural network for a family distributed flexible job shop","authors":"Jiake Li ,&nbsp;Junqing Li ,&nbsp;Ying Xu","doi":"10.1016/j.cie.2024.110855","DOIUrl":"10.1016/j.cie.2024.110855","url":null,"abstract":"<div><div>The distributed flexible job shop scheduling problem (DFJSP) has gained increasing attention in recent years. Meanwhile, the family setup time constraint exists in many realistic manufacturing systems, e.g., prefabricated components system. In this study, first, a mixed integer programming (MIP) model is formulated for the DFJSP with family setup time. To minimize the makespan, a hybrid heterogeneous graph neural network with a principal component analysis (PCA)-based transform mechanism (HGNP) is proposed. In the proposed algorithm, a novel state representation is designed, which combines the features of operation, machine and factory assignment. Then, a multilayer perceptron (MLP) mechanism is used for the operation embedding, and graph attention networks (GATs) are embedded for the machine and factory embeddings. Next, a PCA-based transform mechanism is developed to further fuse all the three embeddings. To improve the solution performance, a simple enhanced local search method is developed. Three different scale of instances are generated to test the performance of HGNP, including small instances to test the effectiveness of the mathematical model, medium and large instances to test the efficiency, and extended public instances to test the generalization abilities. Experimental results and comparisons with different types of state-of-the-art algorithms show the competitiveness and efficiency of the proposed algorithm, both in performance and generalization capabilities.</div></div>","PeriodicalId":55220,"journal":{"name":"Computers & Industrial Engineering","volume":"200 ","pages":"Article 110855"},"PeriodicalIF":6.7,"publicationDate":"2025-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143180304","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}